Forecasting

Bank Note Demand Forecasting

A central bank of Canada runs a distribution network and maintains an inventory of bank notes at regional distribution points for multiple types of denominations. Both shortage and capacity overage of notes at the regional inventories need to be avoided. The goal of this research exploration is to come up with a forecasting model that can help the Bank Note Distribution System (BNDS) operations team to provide the right amount of notes in the right place at the right time.

Domain

Finance / Central Banking

Methods

  • STL Decomposition
  • TBATS
  • Dynamic Harmonic Regression
  • LSTM
  • LightGBM
  • MLP

Tools

  • Python
  • statsmodels
  • Keras
  • LightGBM

Impact / Outcome

Developed multi-model forecasting pipeline comparing classical time series and deep learning approaches for operational demand planning.